Initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.idea/Data_Collection.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.10" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/Data_Collection.iml" filepath="$PROJECT_DIR$/.idea/Data_Collection.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

.idea/workspace.xml

@@ -0,0 +1,53 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ChangeListManager">
+    <list default="true" id="e2d8b51e-654e-4e4e-82ee-2e39a776bb7a" name="Changes" comment="" />
+    <option name="SHOW_DIALOG" value="false" />
+    <option name="HIGHLIGHT_CONFLICTS" value="true" />
+    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
+    <option name="LAST_RESOLUTION" value="IGNORE" />
+  </component>
+  <component name="FileTemplateManagerImpl">
+    <option name="RECENT_TEMPLATES">
+      <list>
+        <option value="Python Script" />
+      </list>
+    </option>
+  </component>
+  <component name="Git.Settings">
+    <option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" />
+  </component>
+  <component name="ProjectColorInfo"><![CDATA[{
+  "associatedIndex": 4
+}]]></component>
+  <component name="ProjectId" id="2oTSyCnM0cuZAAEVnfBnGJXqf8S" />
+  <component name="ProjectViewState">
+    <option name="hideEmptyMiddlePackages" value="true" />
+    <option name="showLibraryContents" value="true" />
+  </component>
+  <component name="PropertiesComponent"><![CDATA[{
+  "keyToString": {
+    "RunOnceActivity.ShowReadmeOnStart": "true",
+    "git-widget-placeholder": "main",
+    "last_opened_file_path": "C:/Users/Owner/PycharmProjects"
+  }
+}]]></component>
+  <component name="SharedIndexes">
+    <attachedChunks>
+      <set>
+        <option value="bundled-python-sdk-d7ad00fb9fc3-c546a90a8094-com.jetbrains.pycharm.community.sharedIndexes.bundled-PC-242.23726.102" />
+      </set>
+    </attachedChunks>
+  </component>
+  <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="application-level" UseSingleDictionary="true" transferred="true" />
+  <component name="TaskManager">
+    <task active="true" id="Default" summary="Default task">
+      <changelist id="e2d8b51e-654e-4e4e-82ee-2e39a776bb7a" name="Changes" comment="" />
+      <created>1730892325122</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1730892325122</updated>
+    </task>
+    <servers />
+  </component>
+</project>

README.md

@@ -0,0 +1,12 @@
+---
+title: Data Collection
+emoji: 🌖
+colorFrom: yellow
+colorTo: yellow
+sdk: gradio
+sdk_version: 5.5.0
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,116 @@
+import gradio as gr
+import os
+import threading
+import random
+from datasets import load_dataset, Dataset, Features, Value
+from huggingface_hub import login
+token = os.getenv("HUGGINGFACE_TOKEN")
+if token:
+    login(token=token)
+else:
+    print("HUGGINGFACE_TOKEN environment variable not set.")
+
+# Set up your Hugging Face dataset name
+dataset_name = "GeorgeIbrahim/EGYCOCO"  # Replace with your dataset name
+
+# Load or create the dataset
+try:
+    dataset = load_dataset(dataset_name)
+except Exception as e:
+    # Create an empty dataset if it doesn't exist
+    features = Features({
+        'image_id': Value(dtype='string'),
+        'caption': Value(dtype='string'),
+    })
+    dataset = Dataset.from_dict({'image_id': [], 'caption': []}, features=features)
+    dataset.push_to_hub(dataset_name)  # Push the empty dataset to Hugging Face
+
+image_folder = "test"
+image_files = [f for f in os.listdir(image_folder) if f.endswith(('.png', '.jpg', '.jpeg'))]
+lock = threading.Lock()
+
+# Function to get a random image that hasn’t been annotated or skipped
+def get_next_image():
+    with lock:
+        available_images = [img for img in image_files]
+        if available_images:
+            return os.path.join(image_folder, random.choice(available_images))
+    return None
+
+# Function to save the annotation to Hugging Face dataset and fetch the next image
+def save_annotation(caption):
+    global current_image
+    if current_image is None:
+        return gr.update(visible=False), gr.update(value="All images have been annotated!")
+
+    with lock:
+        image_id = os.path.basename(current_image)
+
+        # Save caption or "skipped" based on user input
+        if caption.strip().lower() == "skip":
+            caption = "skipped"
+
+        # Add the new annotation to the dataset
+        new_data = {"image_id": image_id, "caption": caption}
+        dataset = dataset.add_item(new_data)
+
+        # Save updated dataset to Hugging Face
+        dataset.push_to_hub(dataset_name)
+
+    # Fetch the next image
+    current_image = get_next_image()
+    if current_image:
+        return gr.update(value=current_image), gr.update(value="")
+    else:
+        return gr.update(visible=False), gr.update(value="All images have been annotated!")
+
+# Function to skip the current image
+def skip_image():
+    global current_image
+    if current_image is None:
+        return gr.update(visible=False), gr.update(value="All images have been annotated!")
+
+    with lock:
+        image_id = os.path.basename(current_image)
+        # Record "skipped" caption directly here
+        new_data = {"image_id": image_id, "caption": "skipped"}
+        dataset = dataset.add_item(new_data)
+
+        # Save updated dataset to Hugging Face
+        dataset.push_to_hub(dataset_name)
+
+    # Fetch the next image
+    current_image = get_next_image()
+    if current_image:
+        return gr.update(value=current_image), gr.update(value="")
+    else:
+        return gr.update(visible=False), gr.update(value="All images have been annotated!")
+
+# Function to initialize the interface
+def initialize_interface():
+    global current_image
+    current_image = get_next_image()
+    if current_image:
+        return gr.update(value=current_image), gr.update(value="")
+    else:
+        return gr.update(visible=False), gr.update(value="All images have been annotated!")
+
+# Build the Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# Image Captioning Tool")
+    gr.Markdown("Please provide a caption for each image displayed. Click 'Submit' after writing your caption, or type 'skip' if you don’t want to annotate this image.")
+
+    with gr.Row():
+        image = gr.Image()
+        caption = gr.Textbox(placeholder="Enter caption here...")
+        submit = gr.Button("Submit")
+        skip = gr.Button("Skip")  # Skip button
+
+    # Define actions for buttons
+    submit.click(fn=save_annotation, inputs=caption, outputs=[image, caption])
+    skip.click(fn=skip_image, inputs=None, outputs=[image, caption])
+
+    # Load initial image
+    demo.load(fn=initialize_interface, inputs=None, outputs=[image, caption])
+
+demo.launch(share=True)